arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.11262cs.CV
收藏

基于对抗性形状学习的VHR遥感图像建筑物提取

Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images

University of Trento(特伦托大学);ETH Zurich(苏黎世联邦理工学院);Technical University of Munich (TUM)(慕尼黑工业大学);German Aerospace Center (DLR)(德国航空航天中心)

Lei Ding, Hao Tang, Yahui Liu, Yilei Shi, Xiao Xiang Zhu, Lorenzo Bruzzone

摘要:

由于遮挡和边界模糊问题,VHR遥感图像中的建筑物提取仍然是一项具有挑战性的任务。虽然传统的基于卷积神经网络(CNN)的方法能够利用局部纹理和上下文信息,但它们无法捕获建筑物的形状模式,这是人类识别中的必要约束。为了解决这个问题,我们提出了一个对抗性形状学习网络(ASLNet)来模拟建筑物形状模式,提高建筑物分割的准确性。在所提出的ASLNet中,我们引入了对抗学习策略来显式地对形状约束进行建模,以及CNN形状正则化器来加强形状特征的嵌入。为了评估建筑物分割结果的几何准确性,我们引入了几个基于对象的质量评估指标。在两个开放的基准数据集上的实验表明,所提出的ASLNet提高了基于像素的精度和基于对象的质量测量的大幅度。代码可在以下网址获得:https://github.com/ggsDing/ASLNet

英文摘要:

Building extraction in VHR RSIs remains a challenging task due to occlusion and boundary ambiguity problems. Although conventional convolutional neural networks (CNNs) based methods are capable of exploiting local texture and context information, they fail to capture the shape patterns of buildings, which is a necessary constraint in the human recognition. To address this issue, we propose an adversarial shape learning network (ASLNet) to model the building shape patterns that improve the accuracy of building segmentation. In the proposed ASLNet, we introduce the adversarial learning strategy to explicitly model the shape constraints, as well as a CNN shape regularizer to strengthen the embedding of shape features. To assess the geometric accuracy of building segmentation results, we introduced several object-based quality assessment metrics. Experiments on two open benchmark datasets show that the proposed ASLNet improves both the pixel-based accuracy and the object-based quality measurements by a large margin. The code is available at: https://github.com/ggsDing/ASLNet

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑